Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Infrasity-Labs/dev-gtm-claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/infrasity-labs/dev-gtm-claude-skills/coding-skills)<a href="https://agentmods.dev/commands/infrasity-labs/dev-gtm-claude-skills/coding-skills"><img src="https://agentmods.dev/badge/commands/infrasity-labs/dev-gtm-claude-skills/coding-skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/infrasity-labs/dev-gtm-claude-skills/coding-skills"><img src="https://agentmods.dev/badge/commands/infrasity-labs/dev-gtm-claude-skills/coding-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00520 |
| Opus 5 | $0.00000 | $0.00260 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
coding-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parse the arguments: $ARGUMENTS
The first word is the subcommand. Everything after it is the input.
Route to the correct skill based on the subcommand:
Code Quality & Review
code-reviewer <repo or file path>— Invoke thecode-reviewerskill. Analyze PRs for complexity and risk, check code quality for SOLID violations and code smells, and generate review reports across 13 languages.pr-review-expert <PR or diff>— Invoke thepr-review-expertskill. Expert-level pull request review for security issues, code quality, and correctness.karpathy-guidelines— Invoke thekarpathy-guidelinesskill. Apply behavioral guidelines to reduce common LLM coding mistakes when writing, reviewing, or refactoring code.
Architecture & Design
senior-architect <system or decision>— Invoke thesenior-architectskill. Design system architecture, evaluate trade-offs (microservices vs monolith, database selection), create architecture diagrams, and produce ADRs.brainstorming <idea or feature>— Invoke thebrainstormingskill. Explore user intent, requirements, and design through dialogue before any implementation work begins.
Development Practices
test-driven-development <feature or bugfix>— Invoke thetest-driven-developmentskill. Write tests first, watch them fail, then write minimal code to pass.using-superpowers— Invoke theusing-superpowersskill. Establish how to find and use available skills at the start of any conversation.
If no subcommand is given or the subcommand is unrecognised, display this help:
Code Quality & Review:
/coding-skills code-reviewer <repo or file> Analyze PRs, detect code smells & SOLID violations
/coding-skills pr-review-expert <PR or diff> Expert PR review for security & quality
/coding-skills karpathy-guidelines Apply guidelines to reduce LLM coding mistakes
Architecture & Design:
/coding-skills senior-architect <system> Design architecture, evaluate trade-offs, create diagrams
/coding-skills brainstorming <idea or feature> Explore requirements and design before building
Development Practices:
/coding-skills test-driven-development <feature> Write tests first, then minimal passing code
/coding-skills using-superpowers Establish skill discovery at session start
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 39 lines · 0 tokens per session scan A 25944da46658
coding-skills is a command published in the GitHub repository Infrasity-Labs/dev-gtm-claude-skills (124 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 520 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
code-review
OWASP-mapped, skill-aware code review with autofix suggestions. Reviews the diff, not the world.
genshijin-review
A compact Japanese-language code-review command that reports one finding per line with a severity label and suggested fix.
review-open-prs
Command "review-open-prs" from The-Artificer-of-Ciphers-LLC/skills-from-the-artificer, covering batch pr review directive — all open prs i did not author, phase a — enumerate target prs & build the queue, phase b — per-pr directive (runs once per queued $pr), 0. context anchoring and 1. preconditions.
review
/review [optional: specific files or PR number].
review-security
Review code or a design for security weaknesses, ranked by real exploitability rather than by checklist coverage.
skill-eval
Validate and audit quality of AI agent slash commands and skills — checks YAML frontmatter, description length, jargon, directive verbs, and duplicates. Run after adding or editing commands.